NIPS Proceedingsβ

Philip S. Thomas

7 Papers

  • A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning (2019)
  • Offline Contextual Bandits with High Probability Fairness Guarantees (2019)
  • Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation (2017)
  • Policy Evaluation Using the Ω-Return (2015)
  • Projected Natural Actor-Critic (2013)
  • Policy Gradient Coagent Networks (2011)
  • TD_gamma: Re-evaluating Complex Backups in Temporal Difference Learning (2011)